Machine learning-based reconstruction of 2D MRI for quantitative morphometry in epilepsy.

Structural neuroimaging analyses require "research quality" images, procured with costly MRI acquisitions. Isotropic (3D-T1) images are desirable for quantitative analyses, however, a routine compromise in the clinical setting is to acquire anisotropic (2D-T1) analogues for qualitative visual inspection. ML (machine learning-based) software have shown promise in addressing some of the limitations of 2D-T1 scans in research applications, yet their efficacy in quantitative research is generally poorly understood. Quantitative morphometric analyses have previously identified pathology-related abnormalities of the subcortical structures in idiopathic generalised epilepsy (IGE), which have been overlooked based on visual inspection. As such, IGE biomarkers present a suitable model in which to evaluate the applicability of image preprocessing methods. This study, therefore, explores subcortical structural biomarkers of IGE, first in our "silver standard" 3D-T1 scans, then in 2D-T1 scans that were either untransformed, resampled using a classical interpolation approach, or synthesised with a resolution and contrast agnostic ML model. 2D-T1 and 3D-T1 MRI scans were acquired during the same scanning session for 33 individuals with drug-sensitive IGE (age